Machine learning predicts perineural invasion in cholangiocarcinoma patients

A novel machine learning model effectively predicts perineural invasion (PNI) in intrahepatic cholangiocarcinoma (ICC) patients preoperatively, offering new insights for clinical decision-making. The XGBoost algorithm demonstrated superior predictive performance, highlighting tumor size, number, and lymph node metastasis as key factors. Significant differences were observed in postoperative outcomes, with better progression-free survival and overall survival in patients without PNI. These findings can enhance personalized treatment strategies for ICC, addressing a critical gap in predictive capabilities.